Agent Marketplace
Ready-made Autoheal agents for every phase of the software lifecycle, from planning to production. Open an agent to see what it does and what it connects to, then get it from GitHub.
- 17 agents
- 5 SDLC phases
- 14 integrations
All agents
17 agents
Incident Response
Investigates a production incident, tests competing explanations in parallel, has the root cause challenged before reporting it, and proposes a bounded mitigation.
Alert Triage
When an alert group fires, links the alerts that fired with it through the service dependency graph, pages the owner of the cause once, and proposes tuning for noisy monitors.
Release Readiness
Reads a release candidate and its diff, checks migrations, canary coverage, error budget and rollback plan, and returns a ship-or-hold verdict with each blocking risk and its owner.
Deploy Verification
After each production deploy, compares error rate, latency and SLO burn against the pre-deploy baseline and last week. On a regression it can attribute to the change, it pages the owner and opens a revert PR.
Vulnerability Remediation
Triages a dependency or container advisory against how your code actually uses it, proves whether the vulnerable path is reachable, and proposes the smallest change that closes it.
Critical CVE Patching
When a critical advisory is published, finds every repository, image and running workload that carries the package, gets the scope approved, opens a patch PR per repository, and reports hourly until nothing vulnerable runs.
PR Risk Review
Reviews each pull request against the service's tier, incident history, SLO and production traffic, scores its risk from 0 to 100, requests the right reviewers, and checks migrations against real table size.
Cloud Cost Optimization
Starts from the bill, attributes each of the largest lines to the service and team that caused it, and only then proposes savings, each with its dollar value and its risk.
Runbook Execution
When a known alert fires, runs its approved runbook once, then checks recovery against the service's SLO for 15 minutes before resolving. If the service has not recovered, it escalates with a log of every action.
Support Escalation Triage
When support escalates a ticket to engineering, replays the customer's session, errors and logs, and matches them to a known issue by stack trace and release. Drafts the reply, or files a reproducible bug when the failure is new.
Service Scorecard
Every week, checks each service against your scorecard (on-call, SLO, monitors, runbook and so on). For each failing rule it opens a pull request that fixes it, with SLO targets taken from the service's own history.
Service Scaffolding
Creates a repository for a new-service request from your golden-path template and checks it against six production-readiness items before handing it over. Also moves older scaffolds to the current template.
EOL Upgrades
Moves every repository in a migration off an end-of-life runtime, toolchain or base image. Pilots the upgrade on one repository per language first, then rolls out tier by tier once approved.
Cost Anomaly Triage
For each daily cost anomaly, finds the deploy, config change, scaling event or traffic change that caused it, names the owning team, and proposes a fix with its dollar impact.
Coding Agent Spend
Every night, prices your coding agents' token usage by type, compares repositories on cost per merged PR, finds where the tokens go, and opens the fix as a pull request.
PR Review Reminders
Keeps one Slack thread per open pull request with its review status and whose turn it is. Reminds only that person, during their working hours, and suggests a reviewer when nobody was requested.
Context Setup
Interviews you to set up and improve a project's context for incident response: checks the integrations, imports services into the Context Graph, writes skills for the project's agents, and scores how ready it is.
Don't see the agent you need?
Build your own. Give it a trigger, a goal and the tools it may use, and Autoheal runs it like any other agent.